Extract PDF text in your browser with LiteParse for the web
Posted by AISignal
LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, using most of the same libraries that LiteParse uses to run in Node.js. Spatial text parsing Refreshin
1 replies
tomspark wrote:
That's pretty slick — browser-side PDF parsing without shipping everything to a server is a solid win for privacy. LlamaIndex has been putting out good stuff lately.